Method and apparatus for predicting service life of engine crankshaft main bearing

Abstract

The application discloses an engine crankshaft main bearing life prediction method and device, and relates to the technical field of engines.The method comprises the following steps: obtaining a vibration signal of an engine crankshaft main bearing, performing one-dimensional deep feature extraction on the segmented vibration signal, and obtaining a characteristic vector; inputting the characteristic vector into a SOM network for training, determining a target optimal neuron and a corresponding weight, and calculating a vibration characteristic life index of the main bearing; obtaining performance parameters of the main bearing, establishing a main bearing life prediction physical model, and calculating a physical model life index of the main bearing; determining a main bearing life comprehensive evaluation index based on the vibration characteristic life index and the physical model life index of the main bearing; and generating a main bearing life prediction curve based on the main bearing life comprehensive evaluation index. The vibration characteristic life index obtained by combining deep learning and the physical model life index obtained by material mechanics are used to predict the life of the crankshaft main bearing, so that the prediction accuracy and reliability are improved.

Description

Technical Field

[0001] This application relates to the field of engine technology, and in particular to a method and device for predicting the life of engine crankshaft main bearings. Background Technology

[0002] As a critical rotating component in an automotive engine, the crankshaft main bearing bears the dual responsibility of transmitting engine power and supporting crankshaft operation. Its performance stability and durability are crucial to the overall engine efficiency and lifespan. During engine operation, the crankshaft main bearing endures complex loads and high-speed rotation. Over time, these loads and frictions lead to wear, fatigue, and even failure. Therefore, accurately predicting the lifespan of the crankshaft main bearing is of great significance for maintaining engine performance and preventing unexpected malfunctions.

[0003] Currently, traditional empirical formula methods for predicting the life of crankshaft main bearings have limited accuracy and are difficult to adapt to complex and ever-changing actual working conditions. They rely too heavily on historical data and are not accurate enough for predicting bearing life under new engines or special working conditions. Traditional finite element analysis methods use engineering software for mechanical analysis to predict the stress and strain distribution of engine crankshaft main bearings under specific working conditions. This includes model building, boundary setting, model debugging, and operational calculations, which requires a large amount of simulation resources, has a long cycle, and high computational costs, making it unsuitable for real-time monitoring and rapid prediction. Traditional machine learning methods are highly dependent on feature engineering, making it difficult to handle high-dimensional data and capture complex patterns in time series, and their accuracy needs to be improved.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method and device for predicting the life of engine crankshaft main bearings, aiming to solve the technical problem of low accuracy in predicting the life of crankshaft main bearings in the prior art.

[0006] To achieve the above objectives, this application provides a method for predicting the life of engine crankshaft main bearings, the method comprising:

[0007] Vibration signals at different times during the entire life cycle of the engine crankshaft main bearing are acquired, and one-dimensional depth feature extraction is performed on the segmented vibration signals to obtain the feature vectors corresponding to the vibration signals.

[0008] The feature vector is input into the SOM network for training, and the target optimal neuron and its weight are determined in the neurons of the SOM network.

[0009] Based on the feature vector and the weight of the target optimal neuron, the vibration characteristic life index of the main bearing is calculated.

[0010] Obtain the performance parameters of the main bearing and establish a physical model for predicting the life of the main bearing;

[0011] Based on the physical model for predicting the life of the main bearing, the physical model life index of the main bearing is calculated.

[0012] Based on the vibration characteristic life index and physical model life index of the main bearing, the comprehensive life evaluation index of the main bearing is determined.

[0013] Based on the comprehensive life evaluation index of the main bearing, a life prediction curve for the main bearing is generated.

[0014] In one embodiment, the step of extracting one-dimensional depth features from the segmented vibration signal to obtain the feature vector corresponding to the vibration signal includes:

[0015] One-dimensional deep features are extracted from the segmented vibration signal using a one-dimensional deep autoencoder feature unit to obtain the feature vector corresponding to the vibration signal. The one-dimensional deep autoencoder feature unit includes an encoding network and a decoding network. The encoding network includes convolutional layers and pooling layers, and the decoding network includes upsampling layers and convolutional layers.

[0016] In one embodiment, the step of inputting feature vectors into a SOM network for training, and determining the target optimal neuron and its weights among the neurons of the SOM network, includes:

[0017] Initialize the SOM network and initialize the weights of the neurons in the SOM network;

[0018] Input the feature vector into the SOM network and calculate the distance between the neuron and the feature vector;

[0019] The neuron with the smallest distance is designated as the optimal neuron, and the neurons other than the optimal neuron are designated as the surrounding neurons.

[0020] Adjust the weights of the optimal neuron and surrounding neurons to make the surrounding neurons gravitate towards the optimal neuron;

[0021] Update the distance between the neuron and the feature vector, and redetermine the best neuron and surrounding neurons. Iterate continuously until the preset conditions are met to obtain the target best neuron and its weight.

[0022] In one embodiment, the step of calculating the vibration characteristic life index of the main bearing based on the feature vector and the weight of the target optimal neuron includes:

[0023] Obtain the first correspondence between the feature vector, the weight of the target optimal neuron, and the vibration feature lifetime index;

[0024] Based on the feature vector, the weight of the target optimal neuron, and the first correspondence, the vibration characteristic life index of the main bearing is determined.

[0025] In one embodiment, the performance parameters include at least the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction factor, main bearing life correction factor, main bearing material correction factor, and lubricating oil characteristic correction factor. The steps of obtaining the main bearing performance parameters and establishing a physical model for predicting the main bearing life include:

[0026] Based on the second correspondence between the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction coefficient, main bearing life correction coefficient, main bearing material correction coefficient, lubricating oil characteristic correction coefficient and physical model life index, the physical model for predicting main bearing life is determined.

[0027] In one embodiment, the step of determining the comprehensive life evaluation index of the main bearing based on the vibration characteristic life index and the physical model life index includes:

[0028] The product of the physical model lifetime index and the safety threshold weight is used as the first index threshold, and the product of the physical model lifetime index and the health threshold weight is used as the second index threshold.

[0029] The sum of the weighted values ​​of the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive weighted value of the index. The weighted value of the vibration characteristic lifetime index is the product of the vibration characteristic lifetime index and its corresponding weight, and the weighted value of the physical model lifetime index is the product of the physical model lifetime index and its corresponding weight.

[0030] Based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, the corresponding decision-making strategy is determined, and based on the decision-making strategy, the comprehensive life evaluation index of the main bearing is determined.

[0031] In one embodiment, the step of determining a corresponding decision strategy based on a first indicator threshold, a second indicator threshold, and a comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy includes:

[0032] When the vibration characteristic life index is less than the first index threshold, the decision strategy is determined to be the smaller one.

[0033] Based on the minimum value strategy, the minimum value between the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive lifetime evaluation index.

[0034] In one embodiment, the step of determining a corresponding decision strategy based on a first indicator threshold, a second indicator threshold, and a comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy includes:

[0035] When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is greater than the second index threshold, the decision strategy is determined to be the weighted average strategy.

[0036] Based on the weighted average strategy, a third correspondence is obtained between vibration characteristic lifetime index, physical model lifetime index, weighting factor and lifetime comprehensive evaluation index.

[0037] Based on the vibration characteristic life index, the physical model life index, the weighting factor of the vibration characteristic life index, the weighting factor of the physical model life index, and the third correspondence, the comprehensive life evaluation index is determined.

[0038] In one embodiment, the step of determining a corresponding decision strategy based on a first indicator threshold, a second indicator threshold, and a comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy includes:

[0039] When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is less than or equal to the second index threshold, the decision strategy is determined to be a dynamic adjustment strategy.

[0040] Based on the dynamic adjustment strategy, a fourth correspondence is obtained between the adjustment coefficient, vibration characteristic lifetime index, physical model lifetime index and lifetime comprehensive evaluation index.

[0041] Based on vibration characteristic life index, physical model life index, adjustment coefficient, and fourth correspondence, a comprehensive life evaluation index is determined.

[0042] Furthermore, to achieve the above objectives, this application also proposes an engine crankshaft main bearing life prediction device, which includes:

[0043] The prediction module is used to acquire vibration signals at different times during the entire life cycle of the engine crankshaft main bearing, and to perform one-dimensional depth feature extraction on the segmented vibration signals to obtain the feature vector corresponding to the vibration signals.

[0044] The prediction module is also used to input feature vectors into the SOM network for training, and to determine the target optimal neuron and the weight of the target optimal neuron in the neurons of the SOM network.

[0045] The prediction module is also used to calculate the vibration characteristic life index of the main bearing based on the feature vector and the weight of the target optimal neuron.

[0046] The prediction module is also used to obtain the performance parameters of the main bearing and to establish a physical model for predicting the life of the main bearing.

[0047] The prediction module is also used to calculate the physical model life index of the main bearing based on the main bearing life prediction physical model.

[0048] The decision module is used to determine the comprehensive life evaluation index of the main bearing based on the vibration characteristic life index and the physical model life index.

[0049] The decision-making module is also used to generate a main bearing life prediction curve based on the comprehensive life evaluation index of the main bearing.

[0050] In addition, to achieve the above objectives, this application also proposes an engine crankshaft main bearing life prediction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the engine crankshaft main bearing life prediction method described above.

[0051] In addition, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the engine crankshaft main bearing life prediction method described above.

[0052] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the engine crankshaft main bearing life prediction method described above.

[0053] This application provides a method for predicting the life of an engine crankshaft main bearing. The method involves acquiring vibration signals at different times throughout the engine crankshaft main bearing's entire lifespan, performing one-dimensional deep feature extraction on the segmented vibration signals to obtain feature vectors corresponding to the vibration signals, inputting these feature vectors into a Surface-Oriented Machine (SOM) network for training, determining the target optimal neuron and its weight within the SOM network's neurons, calculating the vibration characteristic life index of the main bearing based on the feature vectors and the weights of the target optimal neuron, obtaining the main bearing's performance parameters, and establishing a physical model for main bearing life prediction. Based on this physical model, the physical model life index of the main bearing is calculated. Based on the vibration characteristic life index and the physical model life index, a comprehensive life evaluation index for the main bearing is determined. Finally, based on the comprehensive life evaluation index, a main bearing life prediction curve is generated. This application uses a deep learning model to process collected vibration signal data of crankshaft main bearings, extracts the main feature vectors reflecting the degradation state of the equipment, and then integrates the effective features to obtain a vibration characteristic life index that reflects the health of the crankshaft main bearing. Based on the physical model of the crankshaft main bearing and combined with relevant performance parameters, a physical model life index is calculated. Then, the vibration characteristic life index obtained from deep learning and the physical model life index obtained from materials mechanics are combined to obtain a comprehensive life evaluation index for the crankshaft main bearing, and then a life prediction curve for the crankshaft main bearing is constructed to achieve life prediction of the crankshaft main bearing. The deep learning model can capture complex nonlinear patterns, while the physical model provides an intuitive understanding of the equipment state. The effective combination of the advantages of deep learning and physical models improves the accuracy and reliability of prediction, and solves the technical problem of low accuracy in predicting the life of engine crankshaft main bearings. Attached Figure Description

[0054] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating an embodiment of the engine crankshaft main bearing life prediction method of this application;

[0057] Figure 2 This is a schematic diagram of the coding network structure of the engine crankshaft main bearing life prediction method provided in Embodiment 1 of this application;

[0058] Figure 3This is a schematic diagram of the decoding network structure of the engine crankshaft main bearing life prediction method provided in Embodiment 1 of this application;

[0059] Figure 4 This is a flowchart illustrating Embodiment 2 of the engine crankshaft main bearing life prediction method of this application;

[0060] Figure 5 A simplified flowchart illustrating the engine crankshaft main bearing life prediction method provided in Embodiment 2 of this application;

[0061] Figure 6 This is a schematic diagram of the module structure of the engine crankshaft main bearing life prediction device according to an embodiment of this application;

[0062] Figure 7 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the engine crankshaft main bearing life prediction method in this application embodiment.

[0063] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0064] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0065] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0066] The main solution of this application embodiment is as follows: Vibration signals at different times throughout the entire life cycle of the engine crankshaft main bearing are acquired; one-dimensional deep feature extraction is performed on the segmented vibration signals to obtain feature vectors corresponding to the vibration signals; the feature vectors are input into a SOM network for training, and the target optimal neuron and its weight are determined in the neurons of the SOM network; based on the feature vectors and the weights of the target optimal neuron, the vibration characteristic life index of the main bearing is calculated; the performance parameters of the main bearing are acquired, and a physical model for main bearing life prediction is established; based on the physical model for main bearing life prediction, the physical model life index of the main bearing is calculated; based on the vibration characteristic life index and the physical model life index of the main bearing, a comprehensive life evaluation index for the main bearing is determined; based on the comprehensive life evaluation index of the main bearing, a main bearing life prediction curve is generated.

[0067] This application provides a solution that uses a deep learning model to process collected vibration signal data of crankshaft main bearings, extracts the main feature vectors reflecting the degradation state of the equipment, integrates the effective features to obtain a vibration characteristic life index that reflects the health of the crankshaft main bearing, and calculates the physical model life index based on the physical model of the crankshaft main bearing and relevant performance parameters. Then, it combines the vibration characteristic life index obtained from deep learning and the physical model life index obtained from materials mechanics to obtain a comprehensive life evaluation index for the crankshaft main bearing, and then constructs a life prediction curve for the crankshaft main bearing, thus realizing the life prediction of the crankshaft main bearing. The deep learning model can capture complex nonlinear patterns, while the physical model provides an intuitive understanding of the equipment state. The effective combination of the advantages of deep learning and physical models improves the accuracy and reliability of prediction, and solves the technical problem of low accuracy in predicting the life of engine crankshaft main bearings.

[0068] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an engine crankshaft main bearing life prediction device. This embodiment does not specifically limit it in this regard. The following uses an engine crankshaft main bearing life prediction device as an example to describe this embodiment and the following embodiments.

[0069] This application provides a method for predicting the life of an engine crankshaft main bearing, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the engine crankshaft main bearing life prediction method of this application.

[0070] In this embodiment, the method for predicting the life of the engine crankshaft main bearing includes steps S10 to S70:

[0071] Step S10: Obtain vibration signals at different times during the entire life cycle of the engine crankshaft main bearing, and perform one-dimensional depth feature extraction on the segmented vibration signals to obtain the feature vector corresponding to the vibration signals.

[0072] It should be noted that this embodiment collects vibration signals at different times throughout the entire life cycle of the engine crankshaft main bearing for crankshaft main bearing life prediction. The vibration signal data can be angular velocity data or angular acceleration data obtained by sensors, and can be flexibly adjusted according to actual needs; no specific limitation is made.

[0073] Additionally, it should be noted that the collected vibration signals need to be segmented. The length of the segment can be set according to actual needs and is not specifically limited. In this embodiment, the collected vibration signals are segmented according to a length of 2560.

[0074] As can be understood, a feature vector is a vector composed of the features of the vibration signal. The segmented vibration signal undergoes one-dimensional depth feature extraction to obtain the corresponding feature vector.

[0075] In one feasible implementation, the step of extracting one-dimensional depth features from the segmented vibration signal to obtain the feature vector corresponding to the vibration signal includes: extracting one-dimensional depth features from the segmented vibration signal using a one-dimensional depth autoencoder feature unit to obtain the feature vector corresponding to the vibration signal.

[0076] It should be noted that this embodiment uses a one-dimensional deep autoencoder feature unit for one-dimensional deep feature extraction. The one-dimensional deep autoencoder feature unit includes an encoding network and a decoding network. The encoding network includes convolutional layers and pooling layers, and the decoding network includes upsampling layers and convolutional layers. The number of convolutional and pooling layers in the encoding network and the number of upsampling and convolutional layers in the decoding network can be set according to actual needs, and no specific limitation is imposed.

[0077] For example, refer to Figure 2 The encoding module contains 6 convolutional layers (Conv1 to Conv6) and 4 pooling layers (Pool1 to Pool4), see reference. Figure 3 The decoding module has 6 convolutional layers (Conv6~Conv12) and 4 upsampling layers (Upsample1~Upsample4).

[0078] Step S20: Input the feature vector into the SOM network for training, and determine the target optimal neuron and its weight in the neurons of the SOM network.

[0079] In one feasible implementation, step S20 may include steps S201 to S205:

[0080] Step S201: Initialize the SOM network and initialize the weights of the neurons in the SOM network;

[0081] It should be noted that the SOM network consists of an input layer and a competition layer. The competition layer typically contains multiple neurons. When initializing the SOM network, the number of neurons in the competition layer needs to be determined using the following calculation formula:

[0082]

[0083] In the formula, m represents the number of neurons in the competitive layer, and n represents the input feature vector x. h The number of features, k represents the influence factor, which is set according to the actual situation. In this embodiment, the influence factor k is 5.

[0084] Next, the weights of each neuron are initialized.

[0085] Step S202: Input the feature vector into the SOM network and calculate the distance between the neuron and the feature vector;

[0086] Understandably, it is necessary to calculate the distance between each neuron and the feature vector, and the calculation formula is as follows:

[0087] D i =‖x h -w l ||2

[0088] In the formula, D i x represents the distance between the feature vector and the i-th neuron. h w represents the eigenvector. l This represents the weight of a neuron. The distance between each neuron and the feature vector is calculated using the above formula.

[0089] Step S203: Select the neuron with the smallest distance as the optimal neuron, and select the neurons other than the optimal neuron as the surrounding neurons;

[0090] It is understandable that the distances between all the calculated neurons and the feature vectors are sorted, and the neuron with the smallest distance is taken as the best neuron, while the remaining neurons are considered as surrounding neurons.

[0091] Step S204: Adjust the weights of the optimal neuron and the surrounding neurons so that the surrounding neurons move closer to the optimal neuron.

[0092] Understandably, after identifying the optimal neuron and the surrounding neurons, the weights of the optimal neuron and the surrounding neurons are then adjusted to bring the surrounding neurons closer to the optimal neuron.

[0093] Step S205: Update the distance between the neuron and the feature vector, and redetermine the best neuron and surrounding neurons. Iterate continuously until the preset conditions are met to obtain the target best neuron and its weight.

[0094] It should be noted that, as the surrounding neurons converge towards the optimal neuron, the distance between the neuron and the feature vector needs to be recalculated. The optimal neuron and surrounding neurons are then redefined based on the new distance, and their weights are readjusted. This process is iterated continuously until a preset condition is met. The optimal neuron obtained at this point is the final desired optimal neuron, i.e., the target optimal neuron. Simultaneously, the weights of the target optimal neuron need to be determined so that they can be used for subsequent calculations. The preset condition could be reaching the maximum number of iterations; no specific limitation is imposed.

[0095] Step S30: Calculate the vibration characteristic life index of the main bearing based on the feature vector and the weight of the target optimal neuron.

[0096] It should be noted that the vibration characteristic life index is based on vibration signal data processed by deep learning. It extracts the main feature vectors that reflect the degradation state of the equipment, focuses on extracting features from actual monitored vibration data, and can be used to evaluate the life of crankshaft main bearings.

[0097] In one feasible implementation, step S30 may include: obtaining a first correspondence between the feature vector, weights and vibration characteristic life index; and determining the vibration characteristic life index of the main bearing based on the feature vector, the weights of the target optimal neuron and the first correspondence.

[0098] It should be noted that the first correspondence between the feature vector, the weight of the target optimal neuron, and the vibration feature lifetime index, i.e., the calculation formula for the vibration feature lifetime index, is as follows:

[0099] L1 = ||x h -w min ||2

[0100] In the formula, L1 represents the vibration characteristic life index, x h w represents the eigenvector. min This represents the weight of the target optimal neuron.

[0101] Understandably, by substituting the feature vector and the weights of the target optimal neuron into the first correspondence mentioned above, the vibration characteristic life index of the main bearing can be calculated.

[0102] Step S40: Obtain the performance parameters of the main bearing and establish a physical model for predicting the life of the main bearing;

[0103] It should be noted that the main bearing life prediction physical model is the physical model for predicting the life of the main bearing. In this embodiment, the main bearing life prediction physical model is constructed using performance parameters. The selected main bearing performance parameters include at least the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction factor, main bearing life correction factor, main bearing material correction factor, and lubricating oil characteristic correction factor. These parameters can provide comprehensive input data for main bearing life prediction and performance evaluation.

[0104] In one feasible implementation, step S40 may include: determining a physical model for predicting the life of the main bearing based on a second correspondence between the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction coefficient, main bearing life correction coefficient, main bearing material correction coefficient, lubricating oil characteristic correction coefficient and the life index of the physical model.

[0105] It should be noted that the second correspondence between the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction factor, main bearing life correction factor, main bearing material correction factor, lubricating oil characteristic correction factor, and physical model life index, i.e., the calculation relationship satisfied by the physical model life index, is as follows:

[0106]

[0107] In the formula, L2 represents the physical model lifetime index, in hours, and C d Indicates the rated dynamic load of the main bearing, f equ The values ​​represent the actual dynamic load of the main bearing, n represents the crankshaft speed (rpm), ε represents the main bearing life index, β1 represents the main bearing reliability correction factor, β2 represents the main bearing life correction factor, β3 represents the main bearing material correction factor, β4 represents the lubricating oil characteristic correction factor, E represents the elastic modulus of the material, H represents the Brinell hardness of the material, and s ex The material property index is represented by ρ, the density of the lubricating oil is represented by μ, and the dynamic viscosity of the lubricating oil is represented by v. ex This represents the lubricating oil performance index. This embodiment utilizes the aforementioned second correspondence to construct a physical model for predicting main bearing life.

[0108] Additionally, it should be noted that the rated dynamic load C of the main bearing... d This is a theoretical value determined by the bearing manufacturer based on the bearing type, structural dimensions, material properties, and manufacturing process. It represents the maximum load the bearing can withstand under specific conditions without permanent deformation, and is provided in the bearing's product catalog or technical documentation. The actual dynamic load F of the main bearing... equThe bearing life index (ε) refers to the load a bearing withstands under actual operating conditions. It characterizes the stress state of the main bearing and affects the fatigue life of the main bearing material. The main bearing life index is a constant related to the bearing material properties and is usually provided by the bearing manufacturer. The value of the life index may differ for different types of rolling bearings. For example, the life index for ball bearings is typically 3, while the life index for roller bearings is typically 10 / 3, depending on the type and size of the rollers. Bearing life is also related to the crankshaft speed (n), as the speed affects the friction and heat generation inside the bearing, thus affecting the operating state of the main bearing, the average pressure of the main bearing, and the formation of the lubricating oil film. The main bearing life correction factor (β2) is obtained based on the relationship curve between the main bearing's lubricating oil dynamic viscosity ratio, lubricating oil contamination coefficient, and fatigue load limit value, and is provided by the bearing manufacturer.

[0109] Generally, the main bearing reliability correction factor β1 is related to reliability and is influenced by multiple factors such as bearing type, bearing geometry, and material properties. It is provided by the bearing manufacturer, and specific values ​​can be found in Table 1 (this is just an example; other suitable values ​​can also be set). 90% reliability refers to the expected fatigue life (also known as rated life L) that 90% of a sufficiently large number of identical bearings operating under the same conditions will not experience fatigue failure. 10 Correspondingly, 95% reliability refers to the expected fatigue life (also known as rated life L5) of a sufficiently large number of identical bearings operating under the same conditions, where 95% of the bearings do not experience fatigue failure. Typically, rated life L5 is used. 10 As a measure of bearing life, the definition This can be used to determine a bearing size sufficient to avoid fatigue failure. For a given load, using bearing sizes calculated with indicators of high reliability (e.g., 99%) and reliability correction factors can lead to oversized bearings being selected. Higher reliability necessitates larger calculated bearing sizes; therefore, the reliability and reliability correction factors should be flexibly adjusted based on the specific application.

[0110] Table 1

[0111] 90 <![CDATA[L 10 ]]> 1 95 <![CDATA[L5]]> 0.64 96 <![CDATA[L4]]> 0.55 97 <![CDATA[L3]]> 0.47 98 <![CDATA[L2]]> 0.37 99 <![CDATA[L1]]> 0.25

[0112] Understandably, engine main bearings are typically composed of two mating bearing shells, upper and lower. Bearing shells are classified as two-layer or three-layer structures. Two-layer bearings consist of a steel backing and a friction-reducing alloy layer, while three-layer bearings consist of a steel backing, a friction-reducing alloy layer, and a soft-plating layer. Therefore, a main bearing material correction factor β3 needs to be set to characterize the impact of material properties on the main bearing's lifespan. The material's elastic modulus E reflects the elastic properties of the main bearing material, while the Brinell hardness H reflects the surface hardness of the material, affecting the wear characteristics of the main bearing. The material property index s... ex This parameter represents the influence of the main bearing material properties on the main bearing life and needs to be set according to the actual situation.

[0113] Furthermore, it's understandable that lubricating oil characteristic parameters include lubricating oil density, dynamic viscosity, and performance index. These parameters affect the flow state and oil film distribution. Common engine main bearings employ pressure lubrication. During operation, a sufficiently thick oil film forms on the bearing surface to reduce friction and ensure good lubrication performance and service life. Therefore, a lubricating oil characteristic correction factor needs to be set to characterize the impact of these parameters on the main bearing's lifespan. Lubricating oil density ρ affects the stability of the hydrodynamic lubricating oil film in the main bearing; dynamic viscosity μ affects the thickness and load-bearing capacity of the lubricating oil film; and the performance index v... ex This indicates the degree to which the physical properties of the lubricating oil affect the life of the main bearing, and needs to be set according to the actual situation.

[0114] It should be understood that bearing life is actually affected by a combination of factors, such as bearing type, lubrication conditions, bearing installation accuracy, fatigue characteristics of bearing materials, dynamic characteristics of crankshaft, firing order of multi-cylinder engines, bearing geometry, lubrication conditions, bearing clearance, material properties, and environmental factors. Therefore, in practical applications, when constructing a physical model for predicting the life of main bearings, factors such as bearing fatigue life, wear life, and lubrication life can also be considered. The calculation formulas used in the model can be flexibly adjusted according to the actual situation to ensure the reliability and performance optimization of the main bearing design.

[0115] Step S50: Calculate the physical model life index of the main bearing based on the main bearing life prediction physical model.

[0116] It should be noted that the physical model life index focuses on the main bearing performance parameters. The main bearing life prediction physical model is used for calculation to evaluate the life of the crankshaft main bearing.

[0117] Understandably, in practical implementation, the actual values ​​of the main bearing performance parameters are substituted into the physical model for predicting the main bearing life to calculate the physical model life index of the main bearing.

[0118] Step S60: Based on the vibration characteristic life index and physical model life index of the main bearing, determine the comprehensive life evaluation index of the main bearing.

[0119] It should be noted that this embodiment combines the vibration characteristic life index and the physical model life index according to the actual situation to obtain a comprehensive life evaluation index.

[0120] Understandably, deep learning models can capture complex nonlinear patterns, while physical models provide an intuitive understanding of equipment status. This embodiment, based on a deep learning-based vibration signal analysis model and a safety factor based on a physical model, can significantly improve prediction accuracy. Furthermore, since this embodiment does not rely entirely on a single dataset or model assumption, it can generalize to new or unknown situations, exhibiting better generalization ability.

[0121] Step S70: Generate a main bearing life prediction curve based on the comprehensive life evaluation index of the main bearing.

[0122] It should be noted that the final life prediction result is obtained based on the comprehensive life evaluation index of the main bearing.

[0123] This embodiment provides a method for predicting the life of an engine crankshaft main bearing. It involves acquiring vibration signals at different times throughout the engine crankshaft main bearing's entire lifespan, performing one-dimensional deep feature extraction on the segmented vibration signals to obtain feature vectors corresponding to the vibration signals, inputting these feature vectors into a Surface-Oriented Machine (SOM) network for training, determining the target optimal neuron and its weight within the SOM network's neurons, calculating the vibration characteristic life index of the main bearing based on the feature vectors and the weights of the target optimal neuron, obtaining the main bearing's performance parameters, and establishing a physical model for main bearing life prediction. Based on this physical model, the physical model life index of the main bearing is calculated. Based on the vibration characteristic life index and the physical model life index, a comprehensive life evaluation index for the main bearing is determined. Finally, based on the comprehensive life evaluation index, a main bearing life prediction curve is generated. The vibration signal data of the crankshaft main bearing is processed using a deep learning model to extract the main feature vectors reflecting the degradation state of the equipment. Then, the effective features are integrated to obtain a vibration characteristic life index that reflects the health of the crankshaft main bearing. Based on the physical model of the crankshaft main bearing and combined with relevant performance parameters, the physical model life index is calculated. Then, the vibration characteristic life index obtained by deep learning and the physical model life index obtained by mechanics of materials are combined to obtain a comprehensive life evaluation index of the crankshaft main bearing. Finally, the life prediction curve of the crankshaft main bearing is constructed to realize the life prediction of the crankshaft main bearing. The deep learning model can capture complex nonlinear patterns, while the physical model provides an intuitive understanding of the equipment state, effectively combining the advantages of deep learning and physical models.

[0124] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 Step S60 may include steps S601 to S603:

[0125] Step S601: The product of the physical model lifetime index and the safety threshold weight is used as the first index threshold, and the product of the physical model lifetime index and the health threshold weight is used as the second index threshold.

[0126] It should be noted that the first and second indicator thresholds are two thresholds set in this embodiment. The first indicator threshold is the product of the physical model lifetime index L2 and the safety threshold weight α, i.e., L2*α. The second indicator threshold is the product of the physical model lifetime index L2 and the health threshold weight β, i.e., L2*β. The specific values ​​of the safety threshold weight and the health threshold weight need to be determined based on the actual situation, and are not specifically limited thereto.

[0127] Step S602: The sum of the weighted value of the vibration characteristic life index and the weighted value of the physical model life index is used as the comprehensive weighted value of the index;

[0128] It should be noted that the weighted value of the vibration characteristic life index is the value obtained after weighting the vibration characteristic life index. In specific calculations, the weighted value of the vibration characteristic life index is the product of the vibration characteristic life index L1 and its corresponding weight γ1. The weighted value of the physical model life index is the value obtained after weighting the physical model life index. In specific calculations, the weighted value of the physical model life index is the product of the physical model life index L2 and its corresponding weight γ2.

[0129] It is understandable that by adding the weighted value of the vibration characteristic life index to the weighted value of the physical model life index, the comprehensive weighted value of the index can be calculated, that is, the comprehensive weighted value of the index is equal to γ1*L1+γ2*L2.

[0130] Step S603: Based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, determine the corresponding decision strategy, and based on the decision strategy, determine the comprehensive life evaluation index of the main bearing.

[0131] It should be noted that this embodiment sets three key values: the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators. Using these key values, three value ranges are set. Different value ranges are used to calculate the comprehensive life evaluation index in different ways. The decision strategy is the method used to calculate the comprehensive life evaluation index.

[0132] In one feasible implementation, step S603 may include steps A11 to A12:

[0133] Step A11: When the vibration characteristic life index is less than the first index threshold, the decision strategy is determined to be the smaller strategy.

[0134] It should be noted that the "smallest value" strategy refers to selecting the smaller value of the vibration characteristic life index and the physical model life index as the final comprehensive life evaluation index. Under this strategy, the most conservative approach is taken to ensure the safety of the equipment under extreme conditions. By comparing the life evaluation indices predicted by the vibration signal analysis model and the physical analysis model, the smaller value of the two is selected as the final comprehensive life evaluation index. This strategy is suitable for application scenarios with extremely high safety requirements to avoid overly optimistic life predictions.

[0135] It is understandable that if the vibration characteristic life index is less than the first index threshold, i.e., L1 < L2*α, then the smaller strategy is adopted to determine the comprehensive life evaluation index.

[0136] Step A12: Based on the minimum value strategy, the minimum value between the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive lifetime evaluation index.

[0137] Understandably, following the strategy of taking the smaller value, the index with the smaller value between the vibration characteristic lifetime index and the physical model lifetime index is found, i.e., the minimum value is used as the comprehensive lifetime evaluation index, as shown below:

[0138] LPI = min(L1, L2)

[0139] In the formula, LPI represents the comprehensive life evaluation index, L1 represents the vibration characteristic life index, and L2 represents the physical model life index.

[0140] In another feasible implementation, step S603 may include steps B11 to B12:

[0141] Step B11: When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is greater than the second index threshold, the decision strategy is determined to be the weighted average strategy.

[0142] It should be noted that the weighted average strategy refers to assigning different weighting factors to the indicators calculated by two different forecasting methods to calculate the weighted average lifespan. The allocation of weighting factors is based on the importance and reliability assessment of each forecasting method. Therefore, the combined impact of the two forecasting methods can be considered, ensuring that the forecast results of the two methods are weighted according to their reliability and importance, resulting in a more balanced and comprehensive prediction of the main bearing's lifespan.

[0143] Understandably, if the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is greater than the second index threshold, i.e., L1≥L2*α and γ1*L1+γ2*L2>L2*β, then the weighted average strategy is used to calculate the comprehensive life evaluation index.

[0144] Step B12: Based on the weighted average strategy, obtain the third correspondence between the vibration characteristic life index, the physical model life index, the weighting factor and the comprehensive life evaluation index. Based on the vibration characteristic life index, the physical model life index, the weighting factor of the vibration characteristic life index, the weighting factor of the physical model life index and the third correspondence, determine the comprehensive life evaluation index.

[0145] It should be noted that the weighting factor refers to the weight of the vibration characteristic life index / physical model life index in the calculation of the comprehensive life evaluation index. The third correspondence between the vibration characteristic life index, physical model life index, weighting factor, and comprehensive life evaluation index, which is the calculation formula for the comprehensive life evaluation index when using the weighted average strategy, is shown below:

[0146] LPI = w1·L1 + w2·L2

[0147] In the formula, LPI represents the comprehensive life evaluation index, L1 represents the vibration characteristic life index, L2 represents the physical model life index, w1 represents the weighting factor of the vibration characteristic life index, w2 represents the weighting factor of the physical model life index, and w1+w2=1.

[0148] It is understandable that by substituting the vibration characteristic life index, the physical model life index, the weighting factor of the vibration characteristic life index, and the weighting factor of the physical model life index into the third correspondence mentioned above, the comprehensive life evaluation index can be calculated.

[0149] In another feasible implementation, step S603 may include steps C11 to C12:

[0150] Step C11: When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is less than or equal to the second index threshold, the decision strategy is determined to be a dynamic adjustment strategy.

[0151] It should be noted that the dynamic adjustment strategy refers to calculating the comprehensive life evaluation index by introducing an adjustment coefficient. This strategy comprehensively considers the life prediction of two methods and introduces an adjustment coefficient to balance the influence of the two methods, thereby achieving dynamic and adaptive prediction of the main bearing life.

[0152] It is understandable that if the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is less than or equal to the second index threshold, that is, L1≥L2*α and γ1*L1+γ2*L2≤L2*β, then a dynamic adjustment strategy is adopted.

[0153] Step C12: Based on the dynamic adjustment strategy, obtain the fourth correspondence between the adjustment coefficient, vibration characteristic life index, physical model life index and life comprehensive evaluation index. Based on the vibration characteristic life index, physical model life index, adjustment coefficient and the fourth correspondence, determine the life comprehensive evaluation index.

[0154] It should be noted that the fourth correspondence between the adjustment coefficient, vibration characteristic life index, physical model life index, and comprehensive life evaluation index—that is, the calculation formula for the comprehensive life evaluation index when using a dynamic adjustment strategy—is as follows:

[0155]

[0156] In the formula, LPI represents the comprehensive life evaluation index, L1 represents the vibration characteristic life index, L2 represents the physical model life index, and γ represents the adjustment coefficient. Substituting the vibration characteristic life index, physical model life index, and adjustment coefficient into the fourth correspondence above, the comprehensive life evaluation index is calculated.

[0157] Understandably, the adjustment coefficient γ reflects the real-time feedback of the current main bearing operating status or the impact of external environmental factors on its lifespan, and can be dynamically adjusted according to the main bearing operating status and external conditions. When γ > 1, it indicates that the current conditions are conducive to extending the lifespan; when γ < 1, it indicates that the current conditions may shorten the lifespan.

[0158] In summary, this embodiment sets up three decision-making strategies: the minimum strategy, the weighted average strategy, and the dynamic adjustment strategy. The strategy selection method is as follows:

[0159]

[0160] In the formula, L1 represents the vibration characteristic life index, L2 represents the physical model life index, α represents the safety threshold weight, β represents the health threshold weight, γ1 represents the weight of the vibration characteristic life index, and γ2 represents the weight of the physical model life index.

[0161] This embodiment provides a method for predicting the life of an engine crankshaft main bearing. It processes collected vibration signal data of the crankshaft main bearing using a deep learning model, extracts the main feature vectors reflecting the equipment's degradation state, and then integrates these effective features to obtain a vibration characteristic life index that reflects the health of the crankshaft main bearing. Based on the physical model of the crankshaft main bearing and combined with relevant performance parameters, a physical model life index is calculated. Then, the vibration characteristic life index obtained from deep learning and the physical model life index obtained from materials mechanics are combined to obtain a comprehensive life evaluation index for the crankshaft main bearing. Finally, a life prediction curve for the crankshaft main bearing is constructed, thus achieving life prediction of the crankshaft main bearing. The deep learning model can capture complex nonlinear patterns, while the physical model provides an intuitive understanding of the equipment's state, effectively combining the advantages of deep learning and physical models.

[0162] For example, to help understand the implementation process of the engine crankshaft main bearing life prediction method obtained by combining this embodiment with the above-described embodiment two, please refer to... Figure 5 , Figure 5 A simplified flowchart of a method for predicting the life of engine crankshaft main bearings is provided, specifically:

[0163] Step 1: Data preparation, collecting vibration signals at different times during the entire life cycle of the crankshaft main bearing;

[0164] Step 2: One-dimensional depth feature extraction. The segmented vibration signal is input into a one-dimensional depth autoencoder feature unit for training to obtain feature vectors. The one-dimensional depth autoencoder feature unit consists of two parts: an encoding network and a decoding network.

[0165] Step 3: Input the feature vectors into the SOM network for training;

[0166] Step 4: Calculate the life evaluation index 1 of the crankshaft main bearing, denoted as the vibration characteristic life index of the main bearing.

[0167] Step 5: Obtain the performance parameters of the crankshaft main bearing and establish a physical model to evaluate the prediction of the main bearing's life;

[0168] Step 6: Calculate the life evaluation index 2 of the crankshaft main bearing, denoted as the physical model life index of the main bearing.

[0169] Step 7: The crankshaft main bearing life decision unit combines the vibration characteristic life index and the physical model life index of the main bearing according to the actual situation to calculate the comprehensive life evaluation index.

[0170] Step 8: Obtain the crankshaft main bearing life degradation curve.

[0171] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the engine crankshaft main bearing life prediction method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0172] This application also provides an engine crankshaft main bearing life prediction device, please refer to... Figure 6 The engine crankshaft main bearing life prediction device includes:

[0173] Prediction module 10 is used to acquire vibration signals at different times during the entire life cycle of the engine crankshaft main bearing, and to perform one-dimensional depth feature extraction on the segmented vibration signals to obtain the feature vector corresponding to the vibration signals.

[0174] The prediction module 10 is also used to input the feature vector into the SOM network for training, and to determine the target optimal neuron and the weight of the target optimal neuron in the neurons of the SOM network.

[0175] Prediction module 10 is also used to calculate the vibration characteristic life index of the main bearing based on the feature vector and the weight of the target optimal neuron.

[0176] Prediction module 10 is also used to obtain the performance parameters of the main bearing and establish a physical model for predicting the life of the main bearing.

[0177] The prediction module 10 is also used to calculate the physical model life index of the main bearing based on the main bearing life prediction physical model.

[0178] Decision module 20 is used to determine the comprehensive life evaluation index of the main bearing based on the vibration characteristic life index and physical model life index of the main bearing.

[0179] The decision module 20 is also used to generate a main bearing life prediction curve based on the comprehensive life evaluation index of the main bearing.

[0180] In one feasible implementation, the prediction module 10 is further configured to extract one-dimensional deep features from the segmented vibration signal using a one-dimensional deep autoencoder feature unit to obtain the feature vector corresponding to the vibration signal. The one-dimensional deep autoencoder feature unit includes an encoding network and a decoding network. The encoding network includes a convolutional layer and a pooling layer, and the decoding network includes an upsampling layer and a convolutional layer.

[0181] In one feasible implementation, the prediction module 10 is also used to initialize the SOM network and initialize the weights of neurons in the SOM network.

[0182] Input the feature vector into the SOM network and calculate the distance between the neuron and the feature vector;

[0183] The neuron with the smallest distance is designated as the optimal neuron, and the neurons other than the optimal neuron are designated as the surrounding neurons.

[0184] Adjust the weights of the optimal neuron and surrounding neurons to make the surrounding neurons gravitate towards the optimal neuron;

[0185] Update the distance between the neuron and the feature vector, and redetermine the best neuron and surrounding neurons. Iterate continuously until the preset conditions are met to obtain the target best neuron and its weight.

[0186] In one feasible implementation, the prediction module 10 is also used to obtain a first correspondence between the feature vector, the weight of the target optimal neuron and the vibration feature lifetime index.

[0187] Based on the feature vector, the weight of the target optimal neuron, and the first correspondence, the vibration characteristic life index of the main bearing is determined.

[0188] In one feasible implementation, the performance parameters include at least the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction coefficient, main bearing life correction coefficient, main bearing material correction coefficient, and lubricating oil characteristic correction coefficient. The prediction module 10 is also used to determine the main bearing life prediction physical model based on the second correspondence between the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction coefficient, main bearing life correction coefficient, main bearing material correction coefficient, lubricating oil characteristic correction coefficient, and the physical model life index.

[0189] In one feasible implementation, the decision module 20 is further configured to use the product of the physical model lifetime index and the safety threshold weight as the first index threshold, and the product of the physical model lifetime index and the health threshold weight as the second index threshold.

[0190] The sum of the weighted values ​​of the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive weighted value of the index. The weighted value of the vibration characteristic lifetime index is the product of the vibration characteristic lifetime index and its corresponding weight, and the weighted value of the physical model lifetime index is the product of the physical model lifetime index and its corresponding weight.

[0191] Based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, the corresponding decision-making strategy is determined, and based on the decision-making strategy, the comprehensive life evaluation index of the main bearing is determined.

[0192] In one feasible implementation, the decision module 20 is further configured to determine the decision strategy as the smaller strategy when the vibration characteristic life index is less than the first index threshold.

[0193] Based on the minimum value strategy, the minimum value between the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive lifetime evaluation index.

[0194] In one feasible implementation, the decision module 20 is further configured to determine the decision strategy as a weighted average strategy when the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is greater than the second index threshold.

[0195] Based on the weighted average strategy, a third correspondence is obtained between vibration characteristic lifetime index, physical model lifetime index, weighting factor and lifetime comprehensive evaluation index.

[0196] Based on the vibration characteristic life index, the physical model life index, the weighting factor of the vibration characteristic life index, the weighting factor of the physical model life index, and the third correspondence, the comprehensive life evaluation index is determined.

[0197] In one feasible implementation, the decision module 20 is further configured to determine the decision strategy as a dynamic adjustment strategy when the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is less than or equal to the second index threshold.

[0198] Based on the dynamic adjustment strategy, a fourth correspondence is obtained between the adjustment coefficient, vibration characteristic lifetime index, physical model lifetime index and lifetime comprehensive evaluation index.

[0199] Based on vibration characteristic life index, physical model life index, adjustment coefficient, and fourth correspondence, a comprehensive life evaluation index is determined.

[0200] The engine crankshaft main bearing life prediction device provided in this application, employing the engine crankshaft main bearing life prediction method described in the above embodiments, can solve the technical problem of low accuracy in predicting engine crankshaft main bearing life. Compared with the prior art, the beneficial effects of the engine crankshaft main bearing life prediction device provided in this application are the same as those of the engine crankshaft main bearing life prediction method provided in the above embodiments, and other technical features in the engine crankshaft main bearing life prediction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0201] This application provides an engine crankshaft main bearing life prediction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the engine crankshaft main bearing life prediction method in the above embodiment 1.

[0202] The following is for reference. Figure 7This document illustrates a structural schematic diagram suitable for implementing the engine crankshaft main bearing life prediction device according to embodiments of this application. The engine crankshaft main bearing life prediction device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The engine crankshaft main bearing life prediction device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0203] like Figure 7 As shown, the engine crankshaft main bearing life prediction device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the engine crankshaft main bearing life prediction device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the engine crankshaft main bearing life prediction device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an engine crankshaft main bearing life prediction device with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0204] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0205] The engine crankshaft main bearing life prediction device provided in this application, employing the engine crankshaft main bearing life prediction method described in the above embodiments, can solve the technical problem of low accuracy in predicting engine crankshaft main bearing life. Compared with the prior art, the beneficial effects of the engine crankshaft main bearing life prediction device provided in this application are the same as those of the engine crankshaft main bearing life prediction method provided in the above embodiments, and other technical features of this engine crankshaft main bearing life prediction device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0206] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0207] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0208] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the engine crankshaft main bearing life prediction method in the above embodiments.

[0209] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0210] The aforementioned computer-readable storage medium may be included in the engine crankshaft main bearing life prediction device; or it may exist independently and not assembled into the engine crankshaft main bearing life prediction device.

[0211] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the engine crankshaft main bearing life prediction device, the engine crankshaft main bearing life prediction device performs the following actions: acquires vibration signals at different times throughout the engine crankshaft main bearing's entire life cycle; performs one-dimensional deep feature extraction on the segmented vibration signals to obtain feature vectors corresponding to the vibration signals; inputs the feature vectors into a SOM network for training; determines the target optimal neuron and its weight within the SOM network's neurons; calculates the vibration characteristic life index of the main bearing based on the feature vectors and the weights of the target optimal neuron; acquires the performance parameters of the main bearing and establishes a physical model for main bearing life prediction; calculates the physical model life index of the main bearing based on the physical model for main bearing life prediction; determines the comprehensive life evaluation index of the main bearing based on the vibration characteristic life index and the physical model life index; and generates a main bearing life prediction curve based on the comprehensive life evaluation index of the main bearing.

[0212] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0213] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0214] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0215] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described engine crankshaft main bearing life prediction method, thereby solving the technical problem of low accuracy in engine crankshaft main bearing life prediction. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the engine crankshaft main bearing life prediction method provided in the above embodiments, and will not be repeated here.

[0216] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the engine crankshaft main bearing life prediction method described above.

[0217] The computer program product provided in this application can solve the technical problem of low accuracy in predicting the life of engine crankshaft main bearings. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the engine crankshaft main bearing life prediction method provided in the above embodiments, and will not be repeated here.

[0218] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for predicting the life of an engine crankshaft main bearing, characterized in that, The method includes: Vibration signals at different times during the entire life cycle of the engine crankshaft main bearing are acquired, and one-dimensional depth feature extraction is performed on the segmented vibration signals to obtain the feature vector corresponding to the vibration signals. The feature vector is input into the SOM network for training, and the target optimal neuron and the weight of the target optimal neuron are determined in the neurons of the SOM network. Based on the feature vector and the weights of the target optimal neuron, the vibration characteristic life index of the main bearing is calculated. Obtain the performance parameters of the main bearing and establish a physical model for predicting the life of the main bearing; Based on the physical model for predicting the life of the main bearing, the physical model life index of the main bearing is calculated. Based on the vibration characteristic life index and physical model life index of the main bearing, the comprehensive life evaluation index of the main bearing is determined. Based on the comprehensive life evaluation index of the main bearing, a life prediction curve for the main bearing is generated. The step of determining the comprehensive life evaluation index of the main bearing based on the vibration characteristic life index and the physical model life index includes: The product of the physical model lifetime index and the safety threshold weight is used as the first index threshold, and the product of the physical model lifetime index and the health threshold weight is used as the second index threshold. The sum of the weighted value of the vibration characteristic lifetime index and the weighted value of the physical model lifetime index is used as the comprehensive weighted value of the index. The weighted value of the vibration characteristic lifetime index is the product of the vibration characteristic lifetime index and its corresponding weight, and the weighted value of the physical model lifetime index is the product of the physical model lifetime index and its corresponding weight. Based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, a corresponding decision-making strategy is determined, and based on the decision-making strategy, a comprehensive life evaluation index for the main bearing is determined.

2. The method as described in claim 1, characterized in that, The step of performing one-dimensional depth feature extraction on the segmented vibration signal to obtain the feature vector corresponding to the vibration signal includes: One-dimensional deep features are extracted from the segmented vibration signal using a one-dimensional deep autoencoder feature unit to obtain the feature vector corresponding to the vibration signal. The one-dimensional deep autoencoder feature unit includes an encoding network and a decoding network. The encoding network includes convolutional layers and pooling layers, and the decoding network includes upsampling layers and convolutional layers.

3. The method as described in claim 1, characterized in that, The step of inputting the feature vector into the SOM network for training, and determining the target optimal neuron and the weights of the target optimal neuron in the neurons of the SOM network, includes: Initialize the SOM network and initialize the weights of the neurons in the SOM network; The feature vector is input into the SOM network to calculate the distance between the neuron and the feature vector; The neuron with the smallest distance is designated as the optimal neuron, and the neurons other than the optimal neuron are designated as the surrounding neurons. Adjust the weights of the optimal neuron and surrounding neurons to make the surrounding neurons gravitate towards the optimal neuron; The distance between the neuron and the feature vector is updated, and the optimal neuron and surrounding neurons are re-determined. This process is iterated until a preset condition is met, and the target optimal neuron and its weight are obtained.

4. The method as described in claim 1, characterized in that, The step of calculating the vibration characteristic life index of the main bearing based on the feature vector and the weight of the target optimal neuron includes: Obtain the first correspondence between the feature vector, the weight of the target optimal neuron, and the vibration feature lifetime index; Based on the feature vector, the weight of the target optimal neuron, and the first correspondence, the vibration characteristic life index of the main bearing is determined.

5. The method as described in claim 1, characterized in that, The performance parameters include at least the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction factor, main bearing life correction factor, main bearing material correction factor, and lubricating oil characteristic correction factor. The steps of obtaining the main bearing performance parameters and establishing a physical model for main bearing life prediction include: Based on the second correspondence between the main bearing rated dynamic load, actual dynamic load, main bearing life index, crankshaft speed, main bearing reliability correction coefficient, main bearing life correction coefficient, main bearing material correction coefficient, lubricating oil characteristic correction coefficient and physical model life index, the physical model for predicting the main bearing life is determined.

6. The method as described in claim 1, characterized in that, The step of determining the corresponding decision strategy based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy, includes: When the vibration characteristic life index is less than the first index threshold, the decision strategy is determined to be the smaller strategy; Based on the aforementioned minimum value strategy, the minimum value between the vibration characteristic lifetime index and the physical model lifetime index is used as the comprehensive lifetime evaluation index.

7. The method as described in claim 1, characterized in that, The step of determining the corresponding decision strategy based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy, includes: When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is greater than the second index threshold, the decision strategy is determined to be a weighted average strategy. Based on the weighted average strategy, a third correspondence is obtained between the vibration characteristic lifetime index, the physical model lifetime index, the weighting factor and the comprehensive lifetime evaluation index. Based on the vibration characteristic life index, the physical model life index, the weighting factor of the vibration characteristic life index, the weighting factor of the physical model life index, and the third correspondence, the comprehensive life evaluation index is determined.

8. The method as described in claim 1, characterized in that, The step of determining the corresponding decision strategy based on the first indicator threshold, the second indicator threshold, and the comprehensive weighted value of the indicators, and determining the comprehensive life evaluation index of the main bearing based on the decision strategy, includes: When the vibration characteristic life index is greater than or equal to the first index threshold and the comprehensive weighted value of the index is less than or equal to the second index threshold, the decision strategy is determined to be a dynamic adjustment strategy. Based on the dynamic adjustment strategy, a fourth correspondence is obtained between the adjustment coefficient, vibration characteristic lifetime index, physical model lifetime index and lifetime comprehensive evaluation index. Based on the vibration characteristic lifetime index, the physical model lifetime index, the adjustment coefficient, and the fourth correspondence, the comprehensive lifetime evaluation index is determined.

9. A device for predicting the life of an engine crankshaft main bearing, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the engine crankshaft main bearing life prediction method as described in any one of claims 1 to 8.

Images